{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/triplet-based-deep-similarity-learning-for","title":"Triplet-based Deep Similarity Learning for Person Re-Identification","arxiv_id":"1802.03254","date":"2018-02-09","proceeding":null,"authors":["Wentong Liao","Michael Ying Yang","Ni Zhan","Bodo Rosenhahn"],"abstract":"In recent years, person re-identification (re-id) catches great attention in\nboth computer vision community and industry. In this paper, we propose a new\nframework for person re-identification with a triplet-based deep similarity\nlearning using convolutional neural networks (CNNs). The network is trained\nwith triplet input: two of them have the same class labels and the other one is\ndifferent. It aims to learn the deep feature representation, with which the\ndistance within the same class is decreased, while the distance between the\ndifferent classes is increased as much as possible. Moreover, we trained the\nmodel jointly on six different datasets, which differs from common practice -\none model is just trained on one dataset and tested also on the same one.\nHowever, the enormous number of possible triplet data among the large number of\ntraining samples makes the training impossible. To address this challenge, a\ndouble-sampling scheme is proposed to generate triplets of images as effective\nas possible. The proposed framework is evaluated on several benchmark datasets.\nThe experimental results show that, our method is effective for the task of\nperson re-identification and it is comparable or even outperforms the\nstate-of-the-art methods.","url_abs":"http://arxiv.org/abs/1802.03254v1","url_pdf":"http://arxiv.org/pdf/1802.03254v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"triplet-based-deep-similarity-learning-for","repo_url":"https://github.com/ssahn3087/pedestrian_detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"person-re-identification","task_name":"Person Re-Identification"},{"task_slug":null,"task_name":"Triplet"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}